MULTIPLE KERNEL K-MEANS CLUSTERING WITH SIMULTANEOUS SPECTRAL ROTATION

Multiple kernel k-means clustering (MKKM) and its variants have been thoroughly studied over the past decades. However, most existing models utilize a spectrum-based two-step approach to solve the clustering objective, which may deviate from the final cluster labels and lead to suboptimal performance. To address this issue, we elaborate a novel MKKM-R framework that simultaneously optimizes the discrete and continuous cluster labels by incorporating spectral rotation into MKKM. In addition, the proposed model can be easily integrated with other MKKM models to boost their performance. What's more, an efficient alternative algorithm is proposed to solve the joint optimization problem. Extensive experiments on real-world datasets demonstrate the superiorities of the proposed framework.